yaniseuranova
commited on
Commit
•
c7f59db
1
Parent(s):
82965b3
Update README.md
Browse files
README.md
CHANGED
@@ -48,6 +48,8 @@ The goal of this model is to classify users queries in a RAG pipeline between tw
|
|
48 |
and alpha tuning for hybrid search. A query is considered 'semantic' if it doesn't contain any particular jargon, proper noun, technical terms, ect.. on the other hand it is considered lexical
|
49 |
if there are precise keywords than can be used to make a lexical search (BM25 for example).
|
50 |
|
|
|
|
|
51 |
The model was trained using the [SetFit](https://github.com/huggingface/setfit) method that allows Text Classification model finetuning with a reduced number of human annotated training examples. This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
52 |
|
53 |
The model has been trained using an efficient few-shot learning technique that involves:
|
|
|
48 |
and alpha tuning for hybrid search. A query is considered 'semantic' if it doesn't contain any particular jargon, proper noun, technical terms, ect.. on the other hand it is considered lexical
|
49 |
if there are precise keywords than can be used to make a lexical search (BM25 for example).
|
50 |
|
51 |
+
The model is very small and fast, thus enabling a very cost-effective approach for query routing comparing to use large LLMs such as GPT4 for query routing !
|
52 |
+
|
53 |
The model was trained using the [SetFit](https://github.com/huggingface/setfit) method that allows Text Classification model finetuning with a reduced number of human annotated training examples. This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
54 |
|
55 |
The model has been trained using an efficient few-shot learning technique that involves:
|